nvme-multipath: defer partition scanning

We need to suppress the partition scan from occuring within the
controller's scan_work context. If a path error occurs here, the IO will
wait until a path becomes available or all paths are torn down, but that
action also occurs within scan_work, so it would deadlock. Defer the
partion scan to a different context that does not block scan_work.
Reported-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>

drivers/nvme/host/multipath.c

@@ -579,6 +579,20 @@ static int nvme_add_ns_head_cdev(struct nvme_ns_head *head)
 	return ret;
 }
 
+static void nvme_partition_scan_work(struct work_struct *work)
+{
+	struct nvme_ns_head *head =
+		container_of(work, struct nvme_ns_head, partition_scan_work);
+
+	if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN,
+					     &head->disk->state)))
+		return;
+
+	mutex_lock(&head->disk->open_mutex);
+	bdev_disk_changed(head->disk, false);
+	mutex_unlock(&head->disk->open_mutex);
+}
+
 static void nvme_requeue_work(struct work_struct *work)
 {
 	struct nvme_ns_head *head =
@@ -605,6 +619,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
+	INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work);
 
 	/*
 	 * Add a multipath node if the subsystems supports multiple controllers.
@@ -628,6 +643,16 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 		return PTR_ERR(head->disk);
 	head->disk->fops = &nvme_ns_head_ops;
 	head->disk->private_data = head;
+
+	/*
+	 * We need to suppress the partition scan from occuring within the
+	 * controller's scan_work context. If a path error occurs here, the IO
+	 * will wait until a path becomes available or all paths are torn down,
+	 * but that action also occurs within scan_work, so it would deadlock.
+	 * Defer the partion scan to a different context that does not block
+	 * scan_work.
+	 */
+	set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state);
 	sprintf(head->disk->disk_name, "nvme%dn%d",
 			ctrl->subsys->instance, head->instance);
 	return 0;
@@ -654,6 +679,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
+		kblockd_schedule_work(&head->partition_scan_work);
 	}
 
 	mutex_lock(&head->lock);
@@ -973,14 +999,14 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 		return;
 	if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
+		/*
+		 * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
+		 * to allow multipath to fail all I/O.
+		 */
+		synchronize_srcu(&head->srcu);
+		kblockd_schedule_work(&head->requeue_work);
 		del_gendisk(head->disk);
 	}
-	/*
-	 * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
-	 * to allow multipath to fail all I/O.
-	 */
-	synchronize_srcu(&head->srcu);
-	kblockd_schedule_work(&head->requeue_work);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -990,6 +1016,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
+	flush_work(&head->partition_scan_work);
 	put_disk(head->disk);
 }
 

drivers/nvme/host/nvme.h

@@ -494,6 +494,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct work_struct	partition_scan_work;
 	struct mutex		lock;
 	unsigned long		flags;
 #define NVME_NSHEAD_DISK_LIVE	0